Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis
Tuberculosis (TB) is an airborne infectious disease caused by organisms in the <i>Mycobacterium tuberculosis</i> (Mtb) complex. In many low and middle-income countries, TB remains a major cause of morbidity and mortality. Once a patient has been diagnosed with TB, it is critical that hea...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Informatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9709/8/2/27 |
| _version_ | 1797537596387098624 |
|---|---|
| author | Maicon Herverton Lino Ferreira da Silva Barros Geovanne Oliveira Alves Lubnnia Morais Florêncio Souza Elisson da Silva Rocha João Fausto Lorenzato de Oliveira Theo Lynn Vanderson Sampaio Patricia Takako Endo |
| author_facet | Maicon Herverton Lino Ferreira da Silva Barros Geovanne Oliveira Alves Lubnnia Morais Florêncio Souza Elisson da Silva Rocha João Fausto Lorenzato de Oliveira Theo Lynn Vanderson Sampaio Patricia Takako Endo |
| author_sort | Maicon Herverton Lino Ferreira da Silva Barros |
| collection | DOAJ |
| description | Tuberculosis (TB) is an airborne infectious disease caused by organisms in the <i>Mycobacterium tuberculosis</i> (Mtb) complex. In many low and middle-income countries, TB remains a major cause of morbidity and mortality. Once a patient has been diagnosed with TB, it is critical that healthcare workers make the most appropriate treatment decision given the individual conditions of the patient and the likely course of the disease based on medical experience. Depending on the prognosis, delayed or inappropriate treatment can result in unsatisfactory results including the exacerbation of clinical symptoms, poor quality of life, and increased risk of death. This work benchmarks machine learning models to aid TB prognosis using a Brazilian health database of confirmed cases and deaths related to TB in the State of Amazonas. The goal is to predict the probability of death by TB thus aiding the prognosis of TB and associated treatment decision making process. In its original form, the data set comprised 36,228 records and 130 fields but suffered from missing, incomplete, or incorrect data. Following data cleaning and preprocessing, a revised data set was generated comprising 24,015 records and 38 fields, including 22,876 reported cured TB patients and 1139 deaths by TB. To explore how the data imbalance impacts model performance, two controlled experiments were designed using (1) imbalanced and (2) balanced data sets. The best result is achieved by the Gradient Boosting (GB) model using the balanced data set to predict TB-mortality, and the ensemble model composed by the Random Forest (RF), GB and Multi-Layer Perceptron (MLP) models is the best model to predict the cure class. |
| first_indexed | 2024-03-10T12:18:28Z |
| format | Article |
| id | doaj.art-8a358e90567e498886c5703afa5ca90f |
| institution | Directory Open Access Journal |
| issn | 2227-9709 |
| language | English |
| last_indexed | 2024-03-10T12:18:28Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Informatics |
| spelling | doaj.art-8a358e90567e498886c5703afa5ca90f2023-11-21T15:42:28ZengMDPI AGInformatics2227-97092021-04-01822710.3390/informatics8020027Benchmarking Machine Learning Models to Assist in the Prognosis of TuberculosisMaicon Herverton Lino Ferreira da Silva Barros0Geovanne Oliveira Alves1Lubnnia Morais Florêncio Souza2Elisson da Silva Rocha3João Fausto Lorenzato de Oliveira4Theo Lynn5Vanderson Sampaio6Patricia Takako Endo7Programa de Pós-Graduação em Engenharia de Computação (PPGEC), Universidade de Pernambuco, Recife 50720-001, Pernambuco, BrazilPrograma de Pós-Graduação em Engenharia de Computação (PPGEC), Universidade de Pernambuco, Recife 50720-001, Pernambuco, BrazilPrograma de Pós-Graduação em Engenharia de Computação (PPGEC), Universidade de Pernambuco, Recife 50720-001, Pernambuco, BrazilPrograma de Pós-Graduação em Engenharia de Computação (PPGEC), Universidade de Pernambuco, Recife 50720-001, Pernambuco, BrazilPrograma de Pós-Graduação em Engenharia de Computação (PPGEC), Universidade de Pernambuco, Recife 50720-001, Pernambuco, BrazilBusiness School, Dublin City University, Dublin 9, Dublin, IrelandFundação de Medicina Tropical Doutor Heitor Vieira Dourado, Manaus 69040-000, Amazonas, BrazilPrograma de Pós-Graduação em Engenharia de Computação (PPGEC), Universidade de Pernambuco, Recife 50720-001, Pernambuco, BrazilTuberculosis (TB) is an airborne infectious disease caused by organisms in the <i>Mycobacterium tuberculosis</i> (Mtb) complex. In many low and middle-income countries, TB remains a major cause of morbidity and mortality. Once a patient has been diagnosed with TB, it is critical that healthcare workers make the most appropriate treatment decision given the individual conditions of the patient and the likely course of the disease based on medical experience. Depending on the prognosis, delayed or inappropriate treatment can result in unsatisfactory results including the exacerbation of clinical symptoms, poor quality of life, and increased risk of death. This work benchmarks machine learning models to aid TB prognosis using a Brazilian health database of confirmed cases and deaths related to TB in the State of Amazonas. The goal is to predict the probability of death by TB thus aiding the prognosis of TB and associated treatment decision making process. In its original form, the data set comprised 36,228 records and 130 fields but suffered from missing, incomplete, or incorrect data. Following data cleaning and preprocessing, a revised data set was generated comprising 24,015 records and 38 fields, including 22,876 reported cured TB patients and 1139 deaths by TB. To explore how the data imbalance impacts model performance, two controlled experiments were designed using (1) imbalanced and (2) balanced data sets. The best result is achieved by the Gradient Boosting (GB) model using the balanced data set to predict TB-mortality, and the ensemble model composed by the Random Forest (RF), GB and Multi-Layer Perceptron (MLP) models is the best model to predict the cure class.https://www.mdpi.com/2227-9709/8/2/27tuberculosisneglected tropical diseaseprognosismachine learningensemble modelimbalanced data sets |
| spellingShingle | Maicon Herverton Lino Ferreira da Silva Barros Geovanne Oliveira Alves Lubnnia Morais Florêncio Souza Elisson da Silva Rocha João Fausto Lorenzato de Oliveira Theo Lynn Vanderson Sampaio Patricia Takako Endo Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis Informatics tuberculosis neglected tropical disease prognosis machine learning ensemble model imbalanced data sets |
| title | Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis |
| title_full | Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis |
| title_fullStr | Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis |
| title_full_unstemmed | Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis |
| title_short | Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis |
| title_sort | benchmarking machine learning models to assist in the prognosis of tuberculosis |
| topic | tuberculosis neglected tropical disease prognosis machine learning ensemble model imbalanced data sets |
| url | https://www.mdpi.com/2227-9709/8/2/27 |
| work_keys_str_mv | AT maiconhervertonlinoferreiradasilvabarros benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis AT geovanneoliveiraalves benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis AT lubnniamoraisflorenciosouza benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis AT elissondasilvarocha benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis AT joaofaustolorenzatodeoliveira benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis AT theolynn benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis AT vandersonsampaio benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis AT patriciatakakoendo benchmarkingmachinelearningmodelstoassistintheprognosisoftuberculosis |